Smule Renaissance Small: Efficient General-Purpose Vocal Restoration
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866917040662511616 |
|---|---|
| author | Zang, Yongyi Manchester, Chris Young, David Ivanov, Ivan Lufkin, Jeffrey Vladimirov, Martin Solomon, PJ Kepchelev, Svetoslav Chen, Fei Yueh Cai, Dongting Naydenov, Teodor Leistikow, Randal |
| author_facet | Zang, Yongyi Manchester, Chris Young, David Ivanov, Ivan Lufkin, Jeffrey Vladimirov, Martin Solomon, PJ Kepchelev, Svetoslav Chen, Fei Yueh Cai, Dongting Naydenov, Teodor Leistikow, Randal |
| contents | Vocal recordings on consumer devices commonly suffer from multiple concurrent degradations: noise, reverberation, band-limiting, and clipping. We present Smule Renaissance Small (SRS), a compact single-stage model that performs end-to-end vocal restoration directly in the complex STFT domain. By incorporating phase-aware losses, SRS enables large analysis windows for improved frequency resolution while achieving 10.5x real-time inference on iPhone 12 CPU at 48 kHz. On the DNS 5 Challenge blind set, despite no speech training, SRS outperforms a strong GAN baseline and closely matches a computationally expensive flow-matching system. To enable evaluation under realistic multi-degradation scenarios, we introduce the Extreme Degradation Bench (EDB): 87 singing and speech recordings captured under severe acoustic conditions. On EDB, SRS surpasses all open-source baselines on singing and matches commercial systems, while remaining competitive on speech despite no speech-specific training. We release both SRS and EDB under the MIT License. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_21659 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Smule Renaissance Small: Efficient General-Purpose Vocal Restoration Zang, Yongyi Manchester, Chris Young, David Ivanov, Ivan Lufkin, Jeffrey Vladimirov, Martin Solomon, PJ Kepchelev, Svetoslav Chen, Fei Yueh Cai, Dongting Naydenov, Teodor Leistikow, Randal Sound Vocal recordings on consumer devices commonly suffer from multiple concurrent degradations: noise, reverberation, band-limiting, and clipping. We present Smule Renaissance Small (SRS), a compact single-stage model that performs end-to-end vocal restoration directly in the complex STFT domain. By incorporating phase-aware losses, SRS enables large analysis windows for improved frequency resolution while achieving 10.5x real-time inference on iPhone 12 CPU at 48 kHz. On the DNS 5 Challenge blind set, despite no speech training, SRS outperforms a strong GAN baseline and closely matches a computationally expensive flow-matching system. To enable evaluation under realistic multi-degradation scenarios, we introduce the Extreme Degradation Bench (EDB): 87 singing and speech recordings captured under severe acoustic conditions. On EDB, SRS surpasses all open-source baselines on singing and matches commercial systems, while remaining competitive on speech despite no speech-specific training. We release both SRS and EDB under the MIT License. |
| title | Smule Renaissance Small: Efficient General-Purpose Vocal Restoration |
| topic | Sound |
| url | https://arxiv.org/abs/2510.21659 |